metadata
library_name: transformers
license: bsd-3-clause
base_model: shyamgv/blip-image-captioning-large-shyam
tags:
- generated_from_trainer
datasets:
- imagefolder
model-index:
- name: blip-image-captioning-large-shyam-shyam
results: []
blip-image-captioning-large-shyam-shyam
This model is a fine-tuned version of shyamgv/blip-image-captioning-large-shyam on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.0044
- Wer Score: 0.1111
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 15
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Score |
|---|---|---|---|---|
| 0.0104 | 2.9412 | 50 | 0.0041 | 0.1111 |
| 0.0025 | 5.8824 | 100 | 0.0049 | 0.1111 |
| 0.0003 | 8.8235 | 150 | 0.0056 | 0.1667 |
| 0.0002 | 11.7647 | 200 | 0.0045 | 0.1111 |
| 0.0001 | 14.7059 | 250 | 0.0044 | 0.1111 |
Framework versions
- Transformers 4.46.0.dev0
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.20.0